© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 18677
    Prev
    Next
    INDEX
    Explanations

    question

    np_max-act · gemini-2.0-flash

    Instances where the author signals a brief question—e.g., the phrase "quick question" or the token "question" used to introduce a query.

    oai_token-act-pair · gpt-5-mini
    Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     supp
    -0.07
     Św
    -0.07
     lesser
    -0.07
    赶快
    -0.07
    ʰ
    -0.07
    ...............
    -0.07
    .adv
    -0.07
    😞
    -0.06
    {s
    -0.06
    עשה
    -0.06
    POSITIVE LOGITS
     accumulator
    0.07
     Ritch
    0.07
     URI
    0.07
    Currency
    0.07
    Friday
    0.07
    ункци
    0.07
    变量
    0.07
    .virtual
    0.06
    atitis
    0.06
     ISA
    0.06
    Activations Density 0.030%

    No Known Activations